Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    unique and uncommon letter combinations or sequences in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ż
    -0.17
    RITE
    -0.15
    087
    -0.15
    á»ijng
    -0.14
    ounds
    -0.14
    åĩĮ
    -0.14
    ½æķ°
    -0.14
    aps
    -0.14
    awah
    -0.14
    hall
    -0.14
    POSITIVE LOGITS
     Leone
    0.14
    oppable
    0.14
     Sharma
    0.14
    Narrated
    0.14
    hea
    0.14
     Duty
    0.13
    440
    0.13
     Satellite
    0.13
    ceu
    0.13
    -sama
    0.13
    Act Density 0.074%

    No Known Activations